Probing Classifiers: Promises, Shortcomings, and Advances

Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic property from a model's representations -- and has been used to examine a wide variety of models and properties. However, recent studies have demonstrated various methodological weaknesses of this approach. This article critically reviews the probing classifiers framework, highlighting shortcomings, improvements, and alternative approaches.